Instructions to use QuantFactory/Buddy-2B-v1-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use QuantFactory/Buddy-2B-v1-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="QuantFactory/Buddy-2B-v1-GGUF",
	filename="Buddy-2B-v1.Q2_K.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use QuantFactory/Buddy-2B-v1-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf QuantFactory/Buddy-2B-v1-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf QuantFactory/Buddy-2B-v1-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf QuantFactory/Buddy-2B-v1-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf QuantFactory/Buddy-2B-v1-GGUF:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf QuantFactory/Buddy-2B-v1-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf QuantFactory/Buddy-2B-v1-GGUF:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf QuantFactory/Buddy-2B-v1-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf QuantFactory/Buddy-2B-v1-GGUF:Q4_K_M

Use Docker

docker model run hf.co/QuantFactory/Buddy-2B-v1-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use QuantFactory/Buddy-2B-v1-GGUF with Ollama:
```
ollama run hf.co/QuantFactory/Buddy-2B-v1-GGUF:Q4_K_M
```

Unsloth Studio new

How to use QuantFactory/Buddy-2B-v1-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for QuantFactory/Buddy-2B-v1-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for QuantFactory/Buddy-2B-v1-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for QuantFactory/Buddy-2B-v1-GGUF to start chatting

Docker Model Runner
How to use QuantFactory/Buddy-2B-v1-GGUF with Docker Model Runner:
```
docker model run hf.co/QuantFactory/Buddy-2B-v1-GGUF:Q4_K_M
```

Lemonade

How to use QuantFactory/Buddy-2B-v1-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull QuantFactory/Buddy-2B-v1-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Buddy-2B-v1-GGUF-Q4_K_M

List all available models

lemonade list

QuantFactory/Buddy-2B-v1-GGUF

This is quantized version of TheDrummer/Buddy-2B-v1 created using llama.cpp

Original Model Card

I'm serious about the license for this one. NON-COMMERCIAL. Ask permission.

Buddy 2B v1

Disclaimer

Please note that Buddy is not a licensed therapist and should not be relied upon for addressing serious mental health concerns such as depression, trauma, or suicidal thoughts. If you are facing these issues, it is important to seek professional help from a qualified healthcare provider.

Description

Buddy is designed as an empathetic language model, aimed at fostering introspection, self-reflection, and personal growth through thoughtful conversation. Buddy won't judge and it won't dismiss your concerns. Get some self-care with Buddy.

Usage

Chat Format: Gemma or Text Completion
Do not hold back on Buddy.
Open up to Buddy.
Pour your heart out to Buddy.
Listen to Buddy.
Remember that Buddy is just an AI.
You will be assigned a name if you do not provide one.
You can call Buddy anything (e.g., "Hi Alex!").
Buddy isn't perfect, feel free to regenerate responses until one suits you.
You can RP with this:

Downloads last month: 15

GGUF

Model size

3B params

Architecture

gemma2

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support